© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 6273
    Prev
    Next
    INDEX
    Explanations

    references to installation processes and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    følgelig
    -1.18
     varandra
    -1.15
     hvid
    -1.15
     myſelf
    -1.08
     hendes
    -1.06
     houſe
    -1.05
     køb
    -1.05
     themſelves
    -1.04
     whoſe
    -1.04
     ferien
    -1.03
    POSITIVE LOGITS
     på
    0.70
     og
    0.63
     med
    0.60
     som
    0.60
     i
    0.59
     et
    0.58
     en
    0.57
     «
    0.57
     den
    0.53
     del
    0.53
    Activations Density 0.085%

    No Known Activations